projects / platform / upstream / llvm.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: efc6fe9) | patch
[mlir][sparse] run less combinations of SpMM in test (to reduce runtime)
authorAart Bik <ajcbik@google.com>
Fri, 15 Oct 2021 17:07:45 +0000 (10:07 -0700)
committerAart Bik <ajcbik@google.com>
Fri, 15 Oct 2021 23:04:01 +0000 (16:04 -0700)
commite9b1c974be272ca51800cff2cd561f9e53eb127e
tree0a8c71c8e29ab183283974301d58586f8c5eb88ftree | snapshot
parentefc6fe963c114cd9c9436f754ff3e3c2f39041f8commit | diff
[mlir][sparse] run less combinations of SpMM in test (to reduce runtime)

This revision also adds a few passes to the sparse compiler part to unify the transformation sequence with all other paths we currently use.

Reviewed By: nicolasvasilache

Differential Revision: https://reviews.llvm.org/D111900
mlir/test/python/dialects/sparse_tensor/test_SpMM.py diff | blob | history
Domain: System / Toolchain;